Abstract：Objective To validate the feasibility of a deep learning-based clinical target volume (CTV) auto-segmentation algorithm for cervical cancer in clinical settings. Methods CT data sets from 535 cervical cancer patients were collected. CTVs were delineated according to RTOG and JCOG guidelines, reviewed by experts, and then used as reference contours for training (definitive 177, post-operative 302) and test (definitive 23, post-operative 33). Four definitive and 6 post-operative cases were randomly selected from the testing cohort to be manually delineated by junior, intermediate, senior doctors, respectively. Dice coefficient (DSC), mean surface distance (MSD) and Hausdorff distance (HD) were used for test and comparison between auto-segmentation and RO delineation. Meantime, auto-segmentation time and manual delineation time were recorded. Results Auto-segmentation models of dCTV1, dCTV2 and pCTV1 were trained with VB-Net and showed good agreement with reference contours in the testing cohorts (DSC, 0.88,0.70,0.86 mm;MSD,1.32,2.42,1.15 mm;HD,21.6,22.4,20.8 mm). For dCTV1, the difference between auto-segmentation and all three groups of doctors was not significant (P>0.05). For dCTV2 and pCTV1, auto-segmentation was better than the junior and intermediate doctors (both P<0.05). Auto-segmentation time consumption was considerably shorter than that of manual delineation. Conclusions Deep learning-based CTV auto-segmentation algorithm for cervical cancer achieves comparable accuracy to manual delineation of senior doctors. Clinical application of the algorithm can contribute to shortening doctors′ manual delineation time and improving clinical efficiency. Furthermore, it may serve as a guide for junior doctors to improve the consistency and accuracy of cervical cancer CTV delineation in clinical practice.
Ma Chenying,Zhou Juying,Xu Xiaoting et al. Clinical evaluation of deep learning-based clinical target volume auto-segmentation algorithm for cervical cancer[J]. Chinese Journal of Radiation Oncology, 2020, 29(10): 859-865.
[1] Vulquin N, Krause D, Crehange G, et al. MRI guided cervical cancer brachytherapy:inter-and intraobserver variation in hr-ctv delineation in T2-weighted and gadolinium-enhanced T1-weighted images[J]. Int J Radiat Oncol Biol Phys, 2012, 84(3):S431-S432. DOI:10.1016/j.ijrobp.2012.07.1142. [2] Li XA, Tai A, Arthur DW, et al. Variability of target and normal structure delineation for breast-cancer radiotherapy:A RTOG multi-institutional and multi-observer study[J]. Int J Radiat Oncol Biol Phys, 2009, 73(3):944-951. DOI:10.1016/j.ijrobp.2008.10.034. [3] Ng SP, Dyer BA, Kalpathy-Cramer J, et al. A prospective in silico analysis of interdisciplinary and interobserver spatial variability in postoperative target delineation of high-risk oral cavity cancers:Does physician specialty matter?[J]. Clin Transl Radiat Oncol, 2018, 12(1):40-46. DOI:10.1016/j.ctro.2018.07.006. [4] Hong TS, Tomé WA, Harari PM. Heterogeneity in head and neck IMRT target design and clinical practice[J]. Radiother Oncol, 2012, 103(1):92-98. DOI:10.1016/j.radonc.2012.02.010. [5] Harari PM, Song S, Tomé WA. Emphasizing conformal avoidance versus target definition for IMRT planning in head-and-neck cancer[J]. Int J Radiat Oncol Biol Phys, 2010, 77(3):950-958. DOI:10.1016/j.ijrobp.2009.09.062. [6] Tsuji SY, Hwang A, Weinberg V, et al. Dosimetric evaluation of automatic segmentation for adaptive IMRT for Head-and-Neck Cancer[J]. Int J Radiat Oncol Biol Phys, 2010, 77(3):707-714. DOI:10.1016/j.ijrobp.2009.06.012. [7] 蒋晓芹,段宝风,艾平,等. 基于图谱库的自动轮廓勾画软件(ABAS)在鼻咽癌调强放疗中的应用[J]. 中国医学物理学杂志,2013, 30(2):3997-4000. DOI:10.3969/j.issn.1005-202X.2013.02.008. Jiang XQ, Duan BF, AI P, et al. Clinical evaluation of atlas-based autosegementation (ABAS) in NPC intensity-modulated radiotherapy[J]. Chin J Med Phys, 2013, 30(2):3997-4000. DOI:10.3969/j.issn.1005-202X.2013.02.008. [8] 单书灿,邱杰,全红,等. 自动勾画软件对鼻咽癌靶区和危及器官勾画结果对比分析[J]. 中国医学装备, 2015(7):33-36. DOI:10.3969/J. ISSN.1672-8270.2015.07.012. Shan SC, Qiu J, Quan H, et al. Comparison of the two softwares for ABAS in NPC[J]. Chin Med Equip, 2015(7):33-36. DOI:10.3969/J. ISSN.1672-8270.2015.07.012. [9] Cardenas CE, Yang J, Anderson BM, et al. Advances in auto-segmentation[J]. Semin Radiat Oncol, 2019, 29(3):185-197. DOI:10.1016/j.semradonc.2019.02.001. [10] Commowick O, Malandain G. Efficient selection of the most similar image in a database for critical structures segmentation[J]. Med Image Comput Comput Assist Interv, 2007, 10(Pt 2):203-210. DOI:10.1007/978-3-540-75759-7_25. [11] Lin L, Dou Q, Jin YM, et al. Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma[J]. Radiology, 2019, 291(3):677-686. DOI:10.1148/radiol.2019182012. [12] Men K, Chen X, Zhang Y, et al. Deep deconvolutional neural network for target segmentation of nasopharyngeal cancer in planning computed tomography images[J]. Front Oncol, 2017(7):315. DOI:10.3389/fonc.2017.00315. [13] Trebeschi S, van Griethuysen JJM, Lambregts DMJ, et al. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR[J]. Sci Rep, 2017, 7(1):5301. DOI:10.1038/s41598-017-05728-9. [14] Taylor A, Rockally AG, Powell ME. An atlas of the pelvic lymph node regions to aid radiotherapy target volume definition[J]. Clin Oncol, 2007, 19(7):542-550. DOI:10.1016/j.clon.2007.05.002. [15] Toita1 T, Ohno T, Kaneyasu Y, et al. A consensus-based guideline defining clinical target volume for primary disease in external beam radiotherapy for intact uterine cervical cancer[J]. Jpn J Clin Oncol, 2011, 41(9):1119-1126. DOI:10.1093/jjco/hyr096. [16] Milletari F, Navab, N, Ahmadi S. V-Net:fully convolutional neural networks for volumetric medical image segmentation[M]//Fourth International Conference on 3D Vision (3DV). San Francisco:Stanford, CA, 2016:565-571. [17] Carillo V, Cozzarini C, Perna L, et al. Contouring variability of the penile bulb on CT images:quantitative assessment using a generalized concordance index[J]. Int J Radiat Oncol Biol Phys, 2012, 84(3):841-846. DOI:10.1016/j.ijrobp.2011.12.057. Epub 2012 Mar 6. [18] Yousefi S, Kehtarnavaz N, Gholipour A. Improved labeling of subcortical brain structures in atlas-based segmentation of magnetic resonance images[J]. IEEE Trans Biomed Eng, 2012, 59(7):1808-1817. DOI:10.1109/TBME.2011.2122306. Epub 2011 Mar 3. [19] Huttenlocher DP, Klanderman GA, Rucklidge WJ. Comparing images using the Hausdorff distance[J]. IEEE Trans Pattern Anal Mach Intell, 1993, 15(9):850-863. DOI:10.1109/34.232073 [20] 陈建武,刘萍,陈文娟,等. 宫颈癌IMRT靶区及OAR体积与位置变化研究[J]. 中华放射肿瘤学杂志, 2015, 24(4):395-398. DOI:10.3760/cma.j.issn.1004-4221.2015.04.010. Chen JW, Liu P, Chen WJ, et al. A study of changes in volume and location of target areas and organs at risk in intensity-modulated radiotherapy for cervical cancer[J]. Chin J Radiat Oncol, 2015, 24(4):395-398. DOI:10.3760/cma.j.issn.1004-4221.2015.04.010. [21] Meng L, Tian Y, Bu S. Liver tumor segmentation based on 3D convolutional neural network with dual scale[J]. J Appl Clin Med Phys, 2020, 21(1):144-157. DOI:10.1002/acm2.12784. Epub 2019 Dec 2. [22] Wong J, Fong A, McVicar N, et al. Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning[J]. Radiother Oncol,2020,144:152-158. DOI:10.1016/j.radonc.2019.10.019. [23] Veeraraghavan H, Dashevsky BZ, Onishi N, et al. Appearance constrained semi-automatic segmentation from DCE-MRI is reproducible and feasible for breast cancer radiomics:a feasibility study[J]. Sci Rep, 2018, 8(1):4838. DOI:10.1038/s41598-018-22980-9.
2020, Vol. 29 
